Introducing Aerial cuMAC - (Aerial CUDA-Accelerated RAN)

Accelerated Computing Aerial Forum
,
1

cuMAC, a Layer 2 MAC scheduler acceleration library, is developed to improve spectral efficiency by introducing a multi-cell scheduler with enhanced algorithms within Layer 2 of the RAN protocol stack. See link for more details.

2

Hi there,
I am newbie here, try to follow this instruction to setup cuMAC, https://docs.nvidia.com/aerial/cuda-accelerated-ran/aerial_cumac/getting_started.html#getting-and-building-cumac,
on step:
git clone --recurse-submodules https://github.nvidia.com/gputelecom/cumac
got this error:
“Could not resolve host: github.nvidia.com”
Any idea of what’s going wrong?
Any help is highly appreciated.
Thanks.
Sheng

3

Hi @sheng.li,

The cuBB source code folder already includes cuMAC. You can skip git clone step and directly move to the second step as follows:

  1. To build cuMAC, use the following commands:

cd cumac

mkdir build && cd build

cmake ..

make

Let us know if you have any other questions.

Thank you.

4

Hi @bkecicioglu,

Thanks for your reply, I found the cuMAC source code in cuBB, will give it a try.

Thanks.

Sheng